© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6727
    Prev
    Next
    INDEX
    Explanations

    mentions of Cuban athletics at the Pan American Games

    oai_token-act-pair · gemini-2.0-flash

    sporting competitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ComVisible
    -0.75
     olympic
    -0.66
     Olympic
    -0.66
    Olympic
    -0.57
     olymp
    -0.56
     nakalista
    -0.55
     Ause
    -0.54
     Olympics
    -0.53
     Gold
    -0.53
     gold
    -0.52
    POSITIVE LOGITS
     Fußballspieler
    0.59
     Alvaro
    0.58
     ViewGroup
    0.56
     Schenectady
    0.54
     snippetHide
    0.54
    发表于
    0.54
     Bilbao
    0.53
     Alsace
    0.53
    eddable
    0.53
     Guitar
    0.52
    Activations Density 3.382%

    No Known Activations